Non-Invasive Detection of Coronary Artery Disease and Valvular Disorders Using a Multichannel PCG Vest.

The leading cause of mortality and morbidity worldwide is cardiovascular disease (CVD), with coronary artery disease (CAD) being the largest sub-category. Unfortunately, myocardial infarction or stroke can manifest as the first symptom of CAD, underscoring the crucial importance of early disease detection. Hence, there is a global need for a cost-effective, non-invasive, reliable, and easy-to-use system to pre-screen CAD. Previous studies have explored weak murmurs arising from CAD for classification using phonocardiogram (PCG) signals. However, these studies often involve tedious and inconvenient data collection methods, requiring precise subject preparation and environmental conditions. This study proposes using a novel data acquisition system (DAQS) designed for simplicity and convenience. The DAQS incorporates multi-channel PCG sensors into a wearable vest. The entire signal acquisition process can be completed in under two minutes, from fitting the vest to recording signals and removing it, requiring no specialist training. This exemplifies the potential for mass screening, which is impractical with current state-of-the-art protocols. Seven PCG signals are acquired, six from the chest and one from the subject's back, marking a novel approach. Our classification approach, which utilizes linear-frequency cepstral coefficients (LFCC) as features and employs a support vector machine (SVM) to distinguish between normal and CAD-affected heartbeats, outperformed alternative low-computational methods suitable for portable applications. Utilizing feature-level fusion, multiple channels are combined, and the optimal combination yields the highest subject-level accuracy and F1-score of 80.44% and 81.00%, respectively, representing a 7% improvement over the best-performing single channel. The proposed system's performance metrics have been demonstrated to be clinically significant, making the DAQS suitable for practical use. Moreover, the system shows promise in post-procedural monitoring for subjects undergoing percutaneous transluminal coronary angioplasty (PTCA) or coronary artery bypass grafting (CABG), effectively identifying cases of restenosis following intervention.

This paper proposes a quick, compact and cost-effective point-of-care stethoscope-based device that detects Coronary Artery Disease (CAD) from phonocardiogram (PCG) signals, i.e. Recordings of heart sounds, compared to existing methods which are either expensive or are unable to diagnose until the conditions too severe. PCG signals are extracted from patients using a condenser microphone mounted on a stethoscope and is followed by amplification and filtering. The signals are passed through the laptop using an audio jack and digitized. Thereafter they are segmented into the 4 states S1, systole, S2 and diastole using a Hidden Semi Markov Model (HSMM). Afterwards, the diastolic phases are isolated and both time and frequency domain features are analyzed. In the time domain, features are extracted using a nonlinear function, the Automutual Information. In the frequency domain, both high and low-frequency domain features were extracted. A Support Vector Classifier using a Radial Basis Function was trained on 190 recordings from the 2016 PhysioNet/Cinc challenge and obtained an accuracy of 0.74, indicating the combined use of both time and frequency measures from PCG signals could be viable. Such a product could be of great use to clinicians as a quick, inexpensive and primary means of checking whether or not a patient has CAD.

Detection of coronary artery atherosclerotic disease using novel features from synchrosqueezing transform of phonocardiogram

Heart valve disorders (HVDs) are the major causes of cardiovascular diseases (CVD), which may be detected at the early stage using routine auscultation examination. The phonocardiogram (PCG) is a graphical representation of the physiological condition of the heart, which differs with respect to heart diseases. It is closely related to valve functionality which provides vital information for the diagnosis of CVD. However, visual inspection of PCG is tedious and error-prone, which makes it necessary and urgent to develop an automated system for the detection of HVDs with PCG recordings. In the present study we propose a novel method for the identification and classification of normal and abnormal non-segmented PCG recordings based on hybrid signal processing tools and deterministic learning theory. First, PCG signal and its first derivative are decomposed into a set of frequency subbands with a number of decomposition levels by using the tunable Q-factor wavelet transform method. Second, fast and adaptive multivariate empirical mode decomposition decomposes the subbands of the PCG signal and its derivative into scale-aligned intrinsic mode components (IMFs). The first two IMFs are extracted, which contain most of the energy of the PCG signal and its derivative and are considered to be the predominant IMFs. Third, Shannon energy is used to extract the characteristic envelope of predominant IMFs. The properties associated with the nonlinear PCG system dynamics are preserved. They are utilized to derive features, which demonstrate significant difference in PCG system dynamics between normal versus abnormal individual heartbeats. Fourth, neural networks are then used to model, identify and classify PCG system dynamics between normal and abnormal PCG signals based on deterministic learning theory. Finally, experiments have been carried out on a publicly available PCG database to verify the effectiveness of the proposed method, which include two types of classification, one for binary classification (normal vs. abnormal) and the other for multi-class classification (normal vs. aortic stenosis vs. mitral regurgitation vs. mitral stenosis vs. mitral valve prolapse). The overall average accuracy for binary, four-class and five-class classification are reported to be 97.75, 98.69 and 98.48%, respectively. The proposed method has obtained the highest overall accuracy in comparison to other state-of-the-art approaches using the same database, which can serve as an assistant diagnostic tool for the automated detection of HVDs in clinical applications.

Screening for the Presence of Coronary Artery Disease

BackgroundLow physical activity (PA) level and high sedentary time (SED) have been associated to cardiovascular (CVD) morbidity and mortality. Routinely assessing the PA-level of patients being admitted to hospital has been proposed. The aim was to explore PA-level and SED among patients prior to cardiac ward admission and whether this can predict all-cause mortality.MethodsA longitudinal observational study of patients with ischemic heart disease, heart failure, cardiac arrhythmia, valvular heart disorder and inflammatory heart diseases treated on cardiac wards (2015-2016) in Stockholm, Sweden. Data on PA-levels and SED prior to admission were collected by validated questionnaires during inpatient care. PA level a regular week was calculated by an index (3-19 points) including everyday PA and exercise. The cut-off of insufficiently physically active was set to > 9 points. Individuals' reporting ≥7 hours of sitting a normal day were categorised as high SED. Differences in PA-level and SED between different diagnose groups were explored by Benjamini-Hochberg procedure. The associations between PA-level and SED with all-cause mortality were analysed using cox regressions, adjusting for age, sex, diagnosis group, education level, disposable income, smoking status, alcohol consumption and eating habits.ResultsAmong 1148 patients with CVD, approximately 56% were considered as insufficiently physically active (>9 points). In addition, approximately half the study population were categorized as high SED (≥7 hours per day). There were differences in PA-level and SED between the various cardiovascular diagnoses, with individuals with heart failure and valvular heart disorder being in general more inactive and having higher levels of SED. A total of 200 deaths occurred during a median follow-up time of 2.6 years. The mortality was higher among those categorised as insufficiently physically active (HR 1.49, 95% CI 1.08-2.07) or high SED (HR 1.79, 95% CI 1.32-2.43) compared to those reporting sufficient PA and low SED, respectively.ConclusionA high amount reported insufficient PA and a high amount of SED preceding hospitalisation. There was an association between PA (negatively) and SED (positively) with all-cause mortality among patients with CVD. This highlights the prognostic value of assessing patients' PA-level and SED in clinical practice.

Coronary artery disease (CAD) is an irreversible and fatal disease. It necessitates timely and precise diagnosis to slow CAD progression. Electrocardiogram (ECG) and phonocardiogram (PCG), conveying abundant disease-related information, are prevalent clinical techniques for early CAD diagnosis. Nevertheless, most previous methods have relied on single-modal data, restricting their diagnosis precision due to suffering from information shortages. To address this issue and capture adequate information, the development of a multi-modal method becomes imperative. In this study, a novel multi-modal learning method is proposed to integrate both ECG and PCG for CAD detection. Along with deconvolution operation, a novel ECG-PCG coupling signal is evaluated initially to enrich the diagnosis information. After constructing a modified recurrence plot, we build a parallel CNN network to encode multi-modal information, involving ECG, PCG and ECG-PCG coupling deep-coding features. To remove irrelevant information while preserving discriminative features, we add an autoencoder network to compress feature dimension. Final CAD classification is conducted by combining support vector machine and optimal multi-modal features. The experiment is validated on 199 simultaneously recorded ECG and PCG signals from non-CAD and CAD subjects, and achieves high performance with accuracy, sensitivity, specificity and f1-score of 98.49%, 98.57%,98.57% and 98.89%, respectively. The result demonstrates the superiority of the proposed multi-modal method in overcoming information shortages of single-modal signals and outperforming existing models in CAD detection. This study highlights the potential of multi-modal deep-coding information, and offers a wider insight to enhance CAD diagnosis.

Intravenous dipyridamole technetium-99m MMI myocardial perfusion scintigraphy for detection of coronary artery disease.

An efficient and robust Phonocardiography (PCG)-based Valvular Heart Diseases (VHD) detection framework using Vision Transformer (ViT)

Electrocardiogram (ECG) and phonocardiogram (PCG) signals reflect the electrical and mechanical activities of the heart, respectively. Although studies have documented that some abnormalities in ECG and PCG signals are associated with coronary artery disease (CAD), only few researches have combined the two signals for automatic CAD detection. This paper aims to differentiate between CAD and non-CAD groups using simultaneously collected ECG and PCG signals. To entirely exploit the underlying information in these signals, a novel dual-input neural network that integrates the feature extraction and deep learning methods is developed. First, the ECG and PCG features are extracted from multiple domains, and the information gain ratio is used to select important features. On the other hand, the ECG signal and the decomposed PCG signal (at four scales) are concatenated as a five-channel signal. Then, the selected features and the five-channel signal are fed into the proposed network composed of a fully connected model and a deep learning model. The results show that the classification performance of either feature extraction or deep learning is insufficient when using only ECG or PCG signal, and combining the two signals improves the performance. Further, when using the proposed network, the best result is obtained with accuracy, sensitivity, specificity, and G-mean of 95.62%, 98.48%, 89.17%, and 93.69%, respectively. Comparisons with existing studies demonstrate that the proposed network can effectively capture the combined information of ECG and PCG signals for the recognition of CAD.

Integrating multi-domain deep features of electrocardiogram and phonocardiogram for coronary artery disease detection

Current guidelines recommend individually adapted resistance training (RT) as a part of the exercise regime in patients with cardiovascular diseases. The aim of this review was to provide insights into current knowledge and understanding of how useful, feasible, safe, and effective RT is in patients with coronary artery disease (CAD), heart failure (HF), and valvular heart disease (VHD), with particular emphasis on the role of RT in elderly and/or frail patients. A review based on an intensive literature search: systematic reviews and meta-analyses published in 2010 or later; recent studies not integrated into meta-analyses or systematic reviews; additional manual searches. The results highlight the evaluation of effects and safety of RT in patients with CAD and HF with reduced ejection fraction (HFrEF) in numerous meta-analyses. In contrast, few studies have focused on RT in patients with HF with preserved ejection fraction (HFpEF) or VHD. Furthermore, few studies have addressed the feasibility and impact of RT in elderly cardiac patients, and data on the efficacy and safety of RT in frail elderly patients are limited. The review results underscore the high prevalence of age-related sarcopenia, disease-related skeletal muscle deconditioning, physical limitations, and frailty in older patients with cardiovascular diseases (CVD). They underline the need for individually tailored exercise concepts, including RT, aimed at improving functional status, mobility, physical performance and muscle strength in older patients. Furthermore, the importance of the use of assessment tools to diagnose frailty, mobility/functional capacity, and physical performance in the elderly admitted to cardiac rehabilitation is emphasized.

To estimate the excess risk of cardiovascular and cerebrovascular diseases among individuals with ankylosing spondylitis (AS) in Quebec compared with the general population of Quebec. A retrospective cohort study was conducted using population-based administrative data from Quebec. The cohort included all adult individuals with at least 1 AS diagnosis on physician billing or hospital discharge records between 1996 and 2006. A comparison cohort was generated using a 1% random sample of individuals without AS. Cardiovascular and cerebrovascular diseases, and associated hospitalizations, were classified into 1 of 6 subcategories: congestive heart failure, valvular (aortic or nonaortic) heart disease, ischemic heart disease, cerebrovascular disease, or "other" cardiovascular disease. The age- and sex-stratified prevalence estimates, and standardized prevalence ratios, of cardiovascular or cerebrovascular disease in patients with AS, compared to that in the general population, were calculated. The AS cohort included 8,616 individuals diagnosed over the period 1996-2006. The prevalence of cardiovascular and cerebrovascular diseases increased with increasing age for all cardiovascular disease subgroups, and was similar for individuals of both sexes. Age- and sex-stratified prevalence ratios were highest in younger individuals with AS. The age- and sex-standardized prevalence ratios comparing the risk among those with AS to the risk in the general population were as follows: for aortic valvular heart disease 1.58 (95% confidence interval [95% CI] 1.31-1.91), for nonaortic valvular heart disease 1.58 (95% CI 1.43-1.74), for ischemic heart disease 1.37 (95% CI 1.31-1.44), for congestive heart failure 1.34 (95% CI 1.26-1.42), for "other" cardiovascular disease 1.36 (95% CI 1.29-1.44), for cerebrovascular disease 1.25 (95% CI 1.15-1.35), and for any hospitalization for a cardiovascular or cerebrovascular disease 1.31 (95% CI 1.22-1.41). Compared with the general population, patients with AS are at increased risk for many types of cardiovascular and cerebrovascular diseases, and are more likely to be hospitalized for these diseases. The excess risk is greatest in younger patients with AS.

Exercise-induced regional wall motion abnormalities on radionuclide angiography: Lack of reliability for detection of coronary artery disease in the presence of valvular heart disease

BackgroundWe aimed to investigate whether the psychopathological symptoms and temperament-character dimensions observed in patients operated due to coronary artery disease (CAD) or valvular heart disease (VHD) differ among the patients and from healthy individuals.MethodsStudy population was composed of subjects with CAD, VHD and healthy controls (n = 50 in each group). Socio-demographic questionnaire, temperament and character inventory (TCI) and symptom check list-90-R (SCL-90-R) were applied to all groups. Groups were compared about temperament-character dimensions and scores of subscales of SCL-90-R.ResultsHarm avoidance was found to be higher in VHD group than those with CAD and, lower in healthy controls than both patient groups (P = 0.004). Reward dependence was similar among both patient groups and, was higher than healthy group (P = 0.015). Depression, anxiety, somatization, obsession and interpersonal sensitivity were found to be similar in both patient groups but they were higher than those in controls (P < 0.001, P < 0.001, P < 0.001, P = 0.002 and P = 0.003, respectively). Phobia was seen equally in CAD group and healthy controls and, was found to be lower in these than in VHD (P = 0.009). Anger score was in descending order in patients with VHD, CAD and healthy controls group (P = 0.010 and 0.001). Paranoia was in descending order in patients with VHD, CAD and controls (P = 0.015 and 0.001). A weak and inverse correlation was found between ejection fraction (EF) and the persistence dimension of temperament scaled by TCI in patients with VHD (r = -0.276, P = 0.052). An inverse correlation was observed between EF and the reward dependence dimension in CAD group (r = -0.195, P = 0.044). In patients with VHD, EF demonstrated an inversely weak (r = -0.289, P = 0.042), moderate (r = -0.360, P = 0.010) and strong (r = -0.649, P < 0.001) correlation with inter-personal sensitivity, phobia and paranoia, respectively. There was an inverse and weak correlation between EF and depression and anger in VHD group (r = -0.302, P = 0.033 and r = -0.240, P = 0.054).ConclusionVHD and CAD exhibit different psychopathological symptoms and temperament traits. There is a correlation between the aforementioned psychopathological symptoms and temperament traits, and EF.